Update app.py

app.py

@@ -16,10 +16,10 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
 
 def generate_text(question):
-    prompt = f'Q: {question}\nA: '
+    prompt = f'Q: {question}\nA:'
     input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
     tokens = model.generate(input_ids, max_length=22, pad_token_id=tokenizer.eos_token_id)
-    response = tokenizer.decode(tokens[0], skip_special_tokens=True)
+    response = tokenizer.decode(tokens[0], skip_special_tokens=False)
     return response.split('\nA: ')[-1] 
 
 # Gradio Blocks interface